評論
打印
Parlaying genomics and technology into pharmaceutical success is something Cohen has done before.
利用基因組學(xué)和技術(shù)取得制藥成功是科恩以前做過的事情。
He was a cofounder of Millennium Pharmaceuticals, a U.S. oncology-drug maker that helped develop the multiple-myeloma treatment Velcade.
他曾是美國腫瘤藥物制造商千禧制藥公司的聯(lián)合創(chuàng)始人，該公司曾幫助研發(fā)了一款治療多發(fā)性骨髓瘤的藥物Velcade。
Cohen is bullish that Pharnext can be successful with A.I., but he is also aware of the technology's limitations.
科恩看好Pharnext可以與AI取得成功，但他也意識到了這項技術(shù)的局限性。
Google's -AlphaZero, an A.I. program, was able to beat the world's human masters at the Chinese strategy game Go, without using any prior human knowledge.
谷歌的AI程序AlphaZero，能夠在不使用任何先驗人類知識的情況下，在中國圍棋策略游戲中擊敗世界上的人類大師。
But as Cohen points out, Go has a finite set of rules, which AlphaZero knew completely.
但正如科恩所指出的，圍棋有一套有限的規(guī)則，AlphaZero完全清楚這些規(guī)則。
In biology, thanks in part to pleiotropy, the rules are not fully known—and may never be.
在生物學(xué)中，由于基因多效性的原因，其規(guī)則還未被完全了解——并且可能永遠(yuǎn)都不會被了解。
But thoughtfully designed A.I. has enabled Pharnext to build models around the rules that are known and make choices accordingly.
但經(jīng)過精心設(shè)計的AI讓Pharnext能夠圍繞已知的規(guī)則構(gòu)建模型，并據(jù)此做出選擇。
Out of the universe of 10,000 known drugs, the company's discovery model takes in an assortment of 2,000 that are both out of patent and "marketed"—
在一萬種已知藥物中，該公司的發(fā)現(xiàn)模型包含了2000種既已過了專利期又已“上市”的藥物——
that is, already judged both therapeutically effective and safe enough to be sold to the public.
即被判定有療效且足夠安全，可以對公眾進(jìn)行銷售。
To develop its CMT drug, Pharnext first spent about a year assembling its network model for the disease—
為了研發(fā)其CMT藥物，Pharnext首先花了大約一年的時間來組裝這種疾病的網(wǎng)絡(luò)模型——
a framework comparable to GNS's Parkinson's map, showing how nervous and muscular problems "cascade" from the relevant gene mutation.
一種能夠與GNS的帕金森地圖相媲美的框架，呈現(xiàn)的是神經(jīng)和肌肉問題是如何“級聯(lián)”相關(guān)基因突變的。
Based on this mechanism, the computer model arrived at a short list of 57 candidate drugs that addressed various points in the cascade.
基于這種機(jī)制，計算機(jī)模型得到了57種候選藥物的簡短列表，這些候選藥物針對著級聯(lián)中的各個點。
Pharnext tested those drugs one by one in vitro, generating a shorter list of 22 to be tested in mice,
Pharnext對這些藥物逐一進(jìn)行了體外測試，生成了一份更短的清單，其中22種將在老鼠身上進(jìn)行測試，
which finally yielded the three-drug combination that went to human clinical trials.
最終產(chǎn)生了三種藥物的組合，并進(jìn)行了人體臨床試驗。
The recent positive Phase III results confirmed that the PXT3003 cocktail is acting at various points in the cascade.
近期第三期陽性結(jié)果證實了，PXT3003藥物組合正在作用于級聯(lián)中的各個點上。
Without the A.I. model, many more years of preclinical testing would have been required beyond the three years it took Pharnext, says Cohen.
科恩表示，沒有了AI模型，除了Pharnext所花費的三年時間，可能還需要更多時間來進(jìn)行臨床前測試。
"With 2,000 drugs to start with, I could produce all possible combinations, a billion possibilities" to test in vitro.
“根據(jù)一開始的兩千種藥物，我可以制造出所有可能的組合，一百萬種可能”來進(jìn)行體外測試。
That's a recipe for countless false positives and dead ends—years of frustration, for now forestalled.
這就是無數(shù)假陽性和死胡同的秘訣——多年的失望，現(xiàn)在該先發(fā)制人了。
Pharnext's shares, which trade on the Paris stock exchange, have more than doubled since October's Phase III results announcement.
自10月第三階段結(jié)果宣布以來，在巴黎股票交易所交易的Pharnext股票已上漲逾一倍。
The company has spent about 120 million euros ($135 million) over the past decade on research and development—a very modest figure by pharma standards.
在過去的十年里，該公司在研發(fā)上花費了大約1.2億歐元（即1.35億美元）——以制藥行業(yè)的標(biāo)準(zhǔn)來衡量，這是一個非常合理的數(shù)字。
It has never made a profit, but analysts estimate that if PXT3003 reaches the market, revenue—9 million euros in 2018—could soar starting in 2020.
該公司從未實現(xiàn)過盈利，但分析師估計，如果PXT3003上市，該公司的收入——2018年為900萬歐元——將從2020年開始猛增。
(GNS Healthcare is privately held and does not disclose spending or revenue.)
（GNS Healthcare是一家私營企業(yè)，并且沒有披露支出或收入。）
Beyond possible victories for investors, the advances at Pharnext and GNS point the way to A.I.'s growing up—and pharmacology along with it.
除了可能為投資者帶來收益，Pharnext和GNS的進(jìn)步也為AI的發(fā)展指明了道路——藥理學(xué)也隨之而生。
The ability to reason about causality, and to explore counterfactual questions, is a threshold that users of artificial intelligence have long sought to cross.
推理因果關(guān)系，以及探究反設(shè)事實問題的能力，是AI用戶長期以來一直尋求跨越的一道門檻。
The computer models at these startups are making a foray in that direction as they manage and tame a bewildering number of variables.
隨著它們管理并馴服了大量令人眼花繚亂的變量，這些初創(chuàng)公司的計算機(jī)模型正朝著這個方向進(jìn)軍。
Even the underlying definition of disease may evolve. As scientists are learning, these definitions have been overly simplistic.
疾病的基本定義也可能進(jìn)化。隨著科學(xué)家的不斷了解，這些定義被過度簡化了。
A study in the journal Bioinformatics last year noted that attempts to treat tumors
去年《Bioinformatics》期刊上的一項研究指出，
are hampered by the fact that genetic mutations in cancer are "fundamentally heterogeneous":
治療腫瘤的嘗試受到了這樣一個事實的阻礙，即癌癥的基因突變“從根本上是異質(zhì)性的”：
What appears as one disease, or class of disease, in fact contains few commonalities and many differences from patient to patient.
表現(xiàn)為一種疾病或一類疾病的物質(zhì)，實際上幾乎沒有共性，并且病人之間也有許多不同之處。
As it becomes clear that what's happening in any body differs sharply from the "on/off" model of one gene turning on a set of symptoms,
我們越來越清楚，在任何身體中發(fā)生的情況都與一個基因啟動一系列癥狀的“開啟/關(guān)閉”模式截然不同，
technology can help drug developers wrestle with the complexity.
技術(shù)能夠幫助藥物研發(fā)者全力解決這種復(fù)雜性。
Last, but hardly least, these A.I.-driven efforts offer a glimmer of economic hope.
最后但同樣重要的是，這些由AI驅(qū)動的努力帶來了一絲經(jīng)濟(jì)希望。
In an era in which the cost of drug development is a daunting obstacle,
在當(dāng)今時代，藥物研發(fā)成本是一個令人生畏的障礙，
smart algorithms may someday enable medical stakeholders to derive more value from the trillions of dollars that have already been spent on drug research.
聰明的算法將來可能會讓醫(yī)療利益相關(guān)者從已經(jīng)花費在藥物研究上的數(shù)萬億美元中獲得更多的價值。
In theory, with repurposing, "you don't need to design new drugs," Cohen avers. "My feeling is that with 50 drugs, we can treat everything."
理論上，有了再利用，“你就不需要設(shè)計新藥物了，”科恩斷言。“我覺得有了這50種藥物，我們可以治愈一切。”
That would mean changing yet another definition: the meaning of "discovery."
這將意味著改變另一個定義：“發(fā)現(xiàn)”的含義。
譯文由可可原創(chuàng)，僅供學(xué)習(xí)交流使用，未經(jīng)許可請勿轉(zhuǎn)載。
